C#去掉HTML标记

(1)方法一  (未测试)

  public string RemoveHTMLTags(string htmlStream)
        {
            if (htmlStream == null)
            {
                throw new Exception("Your input html stream is null!");
                return null;
            }

            /*
             * 最好把所有的特殊HTML标记都找出来，然后把与其相对应的Unicode字符一起影射到Hash表内，最后一起都替换掉
             */

            //先单独测试,成功后,再把所有模式合并

            //注:这两个必须单独处理
            //去掉嵌套了HTML标记的JavaScript:(<script)[\\s\\S]*(</script>)
            //去掉css标记:(<style)[\\s\\S]*(</style>)
            //去掉css标记:\\..*\\{[\\s\\S]*\\}
            htmlStream = Regex.Replace(htmlStream, "(<script)[\\s\\S]*?(</script>)|(<style)[\\s\\S]*?(</style>)", " ", RegexOptions.IgnoreCase);
            //htmlStream = RemoveTag(htmlStream, "script");
            //htmlStream = RemoveTag(htmlStream, "style");

            //去掉普通HTML标记:<[^>]+>
            //替换空格: |&|瓅 |
            htmlStream = Regex.Replace(htmlStream, "<[^>]+>| |&|瓅 |瓅"|<|>", " ", RegexOptions.IgnoreCase);
            //htmlStream = RemoveTag(htmlStream);

            //替换左尖括号
            //htmlStream = Regex.Replace(htmlStream, "<", "<");

            //替换右尖括号
            //htmlStream = Regex.Replace(htmlStream, ">", ">");

            //替换空行
            //htmlStream = Regex.Replace(htmlStream, "[\n|\r|\t]", " ");//[\n|\r][\t*| *]*[\n|\r]
            htmlStream = Regex.Replace(htmlStream, "(\r\n[\r|\n|\t| ]*\r\n)|(\n[\r|\n|\t| ]*\n)", "\r\n");
            htmlStream = Regex.Replace(htmlStream, "[\t| ]{1,}", " ");

            return htmlStream.Trim();
        }

 

（2）网上搜索到的方法 (可以使用)

 // 除去所有在html元素中标记
    using System.Text.RegularExpressions;
    public static string striphtml(string strhtml)
    {
        string stroutput = strhtml;
        Regex regex = new Regex(@"<[^>]+>|</[^>]+>");

        stroutput = regex.Replace(stroutput, "");
        return stroutput;

    }

转载于:https://www.cnblogs.com/myoungho/archive/2008/06/19/1225972.html